Using Machine Learning Analytics to Deliver Service Levels
September 21, 2016

Jerry Melnick
SIOS Technology

Share this

While the layers of abstraction created in virtualized environments afford numerous advantages, they can also obscure how the virtual resources are best allocated and how physical resources are performing. This can make maintaining optimal application performance a never-ending exercise in trial-and-error.

This post highlights some of the challenges encountered when using traditional monitoring and analytics tools, and describes how machine learning, as a next-generation analytics platform, provides a better way to meet SLAs by finding and fixing issues before they become performance problems. A future post will describe how machine learning analytics can also be used to allocate resources for optimal performance and cost-saving efficiency.

Most IT departments identify performance problems with tools that monitor a variety of discrete events against preset thresholds. For example they set a specific threshold for CPU utilization. Whenever that threshold is exceeded, the tool fires off alerts. But the use of thresholds presents several challenges. They do not account for the interrelated nature of resources in virtualized environments, where a change to or in one can have a significant impact on another. Such interrelationships exist both within and across silos. Without a complete understanding of the environment across silos, users of threshold-based tools frequently discover that their attempts to solve a problem have simply moved it to a different silo.

Thresholds often generate "alert storms" of meaningless data and miss important correlations that might indicate a severe problem exists. They are ineffective in detecting the symptoms of subtle issues that may indicate a significant imminent problem such as "noisy neighbors" or datastore latency issues. These subtle issues may not exceed a threshold related to the root cause or may exceed a threshold in short, random intervals, producing alerts that are frequently lost amid the "noise" of alert storms.

Even the so-called dynamic thresholds cannot accommodate the constant change in dynamic environments and, as a result, require significant ongoing IT intervention. And finally, while they may alert IT to an issue, they rarely provide sufficiently actionable information for resolving it. The exponential growth in the size and complexity of virtual environments has outstripped the ability of IT staff to set, manage, and continuously adjust threshold-based tools effectively. The time for an automated solution has come.

Advanced machine learning-based analytics software overcomes these and other challenges by continuously learning the many complex behaviors and interactions among interrelated objects – CPU, storage, network, applications – across the infrastructure. Unlike threshold-based solutions, this growing knowledge enables machine learning-based IT analytics solutions to provide a highly accurate means of identifying the root cause(s) of performance problems and making specific recommendations for resolving them cost-effectively.

This ability to aggregate, normalize, and then correlate and analyze hundreds of thousands of data points from different monitoring and management systems enable machine learning analytics solutions to transform massive volumes of data into meaningful insights across applications, servers and hosts, and storage and network infrastructures.

As it gathers and analyzes this wealth of data, the MLA system learns what constitutes normal behaviors, and it is this baseline that gives the system the ability to detect anomalies and find root causes automatically.

In addition to identifying root causes, advance machine learning based analytics solutions are able to simulate and predict the impact of making certain changes in resources and their allocations, which can be particularly useful for optimizing resource utilization and planning for expansion. This capability can also be useful for assessing if there is adequate capacity to handle a partial or complete failover. And these are topics worthy of a deeper dive in a future post.

Jerry Melnick is President and CEO of SIOS Technology.

Share this

The Latest

November 17, 2017

Just in time for the holiday shopping season, APMdigest asked experts from across the industry for their opinions on the best way to measure eCommerce performance, in terms of applications, networks and infrastructure. Part 3, the final installment, covers the customer journey ...

November 16, 2017

Just in time for the holiday shopping season, APMdigest asked experts from across the industry for their opinions on the best way to measure eCommerce performance, in terms of applications, networks and infrastructure. Part 2 covers APM and monitoring ...

November 15, 2017

As the holiday shopping season looms ahead, and online sales are positioned to challenge or even beat in-store purchases, eCommerce is on the minds of many decision makers. To help organizations decide how to gauge their eCommerce success, APMdigest compiled a list of expert opinions on the best way to measure eCommerce performance ...

November 14, 2017

More than 90 percent of respondents are concerned about data and application security in public clouds while nearly 60 percent of respondents reported that public cloud environments make it more difficult to obtain visibility into data traffic, according to a new Cloud Security survey ...

November 13, 2017

Today's technology advances have enabled end-users to operate more efficiently, and for businesses to more easily interact with customers and gather and store huge amounts of data that previously would be impossible to collect. In kind, IT departments can also collect valuable telemetry from their distributed enterprise devices to allow for many of the same benefits. But now that all this data is within reach, how can organizations make sense of it all? ...

November 09, 2017

CIOs trying to lead digital transformation at the speed needed to succeed need a mix of three scale accelerators, according to Gartner, Inc. The three scale accelerators include: digital dexterity, network effect technologies, and an industrialized digital platform ...

November 08, 2017

While the majority of IT practitioners in the UK believe their organization is equipped to support digital services, over half of them also say they face consumer-impacting incidents at least one or more times a week, sometimes costing their organizations millions in lost revenue for every hour that an application is down, according to PagerDuty's State of Digital Operations Report: United Kingdom ...

November 07, 2017

Today's IT is under considerable pressure to remain agile, responsive and scalable to meet the changing needs of business. IT infrastructure can't become a bottleneck, it must be the enabler. But as new paradigms, such as DevOps, are adopted, data center complexity increases and infrastructure constraints can block the ability to achieve these goals ...

November 06, 2017

It's 3:47am. You and the rest of the Ops team have been summoned from your peaceful slumber to mitigate an application delivery outage. Your mind races as you switch to problem solving mode. It's time to start thinking about how to make this mitigation FUN! ...

November 03, 2017

With the increased complexity of IT environments, the rising cyber threats and the growing number of IT alerts, IT organizations have come to the realization that throwing more people at IT issues doesn't solve the problem ...